commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Phil Steitz (JIRA)" <j...@apache.org>
Subject [jira] [Closed] (MATH-1189) SimpleRegression may not report fit statistics correctly for perfect linear models
Date Sun, 11 Jan 2015 22:15:34 GMT

     [ https://issues.apache.org/jira/browse/MATH-1189?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Phil Steitz closed MATH-1189.
-----------------------------
    Resolution: Invalid

The test failure in the description is caused by incorrect cumulative probability computation
in the t distribution on the host that generated the test failure.  If there is a bug somewhere,
it is in the t distrbution, not this class.

> SimpleRegression may not report fit statistics correctly for perfect linear models
> ----------------------------------------------------------------------------------
>
>                 Key: MATH-1189
>                 URL: https://issues.apache.org/jira/browse/MATH-1189
>             Project: Commons Math
>          Issue Type: Bug
>            Reporter: Phil Steitz
>             Fix For: 3.4.2
>
>
> The getSignificance(), getRSquare() and getR() methods can return infinite values when
they should return 0, 1 and 1 respectively if the sum of squared errors is exactly 0.
> From Jenkins test run:
> {code}
> java.lang.AssertionError: expected:<0.0> but was:<Infinity>
> 	at org.junit.Assert.fail(Assert.java:88)
> 	at org.junit.Assert.failNotEquals(Assert.java:743)
> 	at org.junit.Assert.assertEquals(Assert.java:494)
> 	at org.junit.Assert.assertEquals(Assert.java:592)
> 	at org.apache.commons.math3.stat.regression.SimpleRegressionTest.testPerfect(SimpleRegressionTest.java:546)
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message